Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update business_standard_print.recipe

Browse Source
This commit is contained in:
unkn0w7n 2025-05-10 14:21:38 +05:30
parent 04642ffda9
commit 07db492808
1 changed files with 42 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
recipes/business_standard_print.recipe
View File

@ -38,15 +38,19 @@ class BusinessStandardPrint(BasicNewsRecipe):
recipe_specific_options = { recipe_specific_options = {
'date': { 'date': {
'short': 'The date of the print edition to download (DD-MM-YYYY format)', 'short': 'The date of the print edition to download (DD-MM-YYYY format)',
'long': 'For example, 20-09-2023' 'long': 'For example, 20-09-2023',
} }
} }
def get_cover_url(self): def get_cover_url(self):
d = self.recipe_specific_options.get('date') d = self.recipe_specific_options.get('date')
if not (d and isinstance(d, str)): if not (d and isinstance(d, str)):
soup = self.index_to_soup('https://www.magzter.com/IN/Business-Standard-Private-Ltd/Business-Standard/Newspaper/') soup = self.index_to_soup(
for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')): 'https://www.magzter.com/IN/Business-Standard-Private-Ltd/Business-Standard/Newspaper/'
)
for citem in soup.findAll(
'meta', content=lambda s: s and s.endswith('view/3.jpg')
):
return citem['content'] return citem['content']
def parse_index(self): def parse_index(self):
@ -81,7 +85,7 @@ class BusinessStandardPrint(BasicNewsRecipe):
desc = article['sub_heading'] desc = article['sub_heading']
url = 'https://www.business-standard.com' + article['article_url'] url = 'https://www.business-standard.com' + article['article_url']
self.log('\t', title, '\n\t', desc, '\n\t\t', url) self.log('\t', title, '\n\t', desc, '\n\t\t', url)
articles.append({'title': title, 'description':desc, 'url': url}) articles.append({'title': title, 'description': desc, 'url': url})
if articles: if articles:
feeds.append((section, articles)) feeds.append((section, articles))
return feeds return feeds
@ -105,33 +109,59 @@ class BusinessStandardPrint(BasicNewsRecipe):
cat = subhead = lede = auth = caption = '' cat = subhead = lede = auth = caption = ''
if 'defaultArticleCat' in data and data['defaultArticleCat'] is not None: if 'defaultArticleCat' in data and data['defaultArticleCat'] is not None:
if 'h1_tag' in data['defaultArticleCat'] and data['defaultArticleCat']['h1_tag'] is not None: if (
'h1_tag' in data['defaultArticleCat']
and data['defaultArticleCat']['h1_tag'] is not None
):
cat = '<div class="cat">' + data['defaultArticleCat']['h1_tag'] + '</div>' cat = '<div class="cat">' + data['defaultArticleCat']['h1_tag'] + '</div>'
if 'metaDescription' in data and data['metaDescription'] is not None: if 'metaDescription' in data and data['metaDescription'] is not None:
subhead = '<p class="sub">' + data['metaDescription'] + '</p>' subhead = '<p class="sub">' + data['metaDescription'] + '</p>'
self.art_desc = data['metaDescription'] self.art_desc = data['metaDescription']
date = (datetime.fromtimestamp(int(data['publishDate']))).strftime('%b %d, %Y | %I:%M %p') date = (datetime.fromtimestamp(int(data['publishDate']))).strftime(
'%b %d, %Y | %I:%M %p'
)
authors = [] authors = []
if 'articleMappedMultipleAuthors' in data: if 'articleMappedMultipleAuthors' in data:
for aut in data['articleMappedMultipleAuthors']: for aut in data['articleMappedMultipleAuthors']:
authors.append(data['articleMappedMultipleAuthors'][str(aut)]) authors.append(data['articleMappedMultipleAuthors'][str(aut)])
auth = '<div><p class="auth">' + ', '.join(authors) + ' | ' + data['placeName'] + ' | ' + date + '</p></div>' auth = (
'<div><p class="auth">'
+ ', '.join(authors)
+ ' | '
+ data['placeName']
+ ' | '
+ date
+ '</p></div>'
)
if 'featuredImageObj' in data: if 'featuredImageObj' in data:
if 'url' in data['featuredImageObj']: if 'url' in data['featuredImageObj']:
if img_url is not None: if img_url is not None:
lede = '<p class="cap"><img src="{}">'.format(img_url) lede = '<p class="cap"><img src="{}">'.format(img_url)
else: else:
lede = '<p class="cap"><img src="{}">'.format(data['featuredImageObj']['url']) lede = '<p class="cap"><img src="{}">'.format(
data['featuredImageObj']['url']
)
if 'alt_text' in data['featuredImageObj']: if 'alt_text' in data['featuredImageObj']:
caption = '<span>' + data['featuredImageObj']['alt_text'] + '</span></p>' caption = '<span>' + data['featuredImageObj']['alt_text'] + '</span></p>'
body = data['htmlContent'] body = data['htmlContent']
return '<html><body>' + cat + title + subhead + auth + lede + caption + '<div><br>' + body + '</div></body></html>' return (
'<html><body>'
+ cat
+ title
+ subhead
+ auth
+ lede
+ caption
+ '<div><br>'
+ body
+ '</div></body></html>'
)
def preprocess_html(self, soup): def preprocess_html(self, soup):
for img in soup.findAll('img'): for img in soup.findAll('img'):
@ -141,4 +171,7 @@ class BusinessStandardPrint(BasicNewsRecipe):
for attr in self.remove_attributes: for attr in self.remove_attributes:
for x in soup.findAll(attrs={attr: True}): for x in soup.findAll(attrs={attr: True}):
del x[attr] del x[attr]
for br in soup.findAll('small', attrs={'class': 'brtag'}):
br.name = 'br'
br.clear()
return soup return soup